7.5
/ 10
HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Description
vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1.
Basic Information
ID
CVE-2025-48956
Source
GitHub_M
Published
Aug 21, 2025 at 14:41
Modified
Aug 21, 2025 at 15:02
Affected Product
Vendor
vllm-project
Product
vllm
Version
>= 0.1.0, < 0.10.1.1
Affected Versions
vllm-project vllm >= 0.1.0, < 0.10.1.1